Adaptive Temporal Graph Neural Networks for Real-Time Financial Fraud Detection under Concept Drift
Highlights in Business, Economics and Management · 10.09.2026 · 69 · 239-250
DOI: 10.54097/c8364y03 ↗Kurz gefasst
Fachartikel in der Zeitschrift Highlights in Business, Economics and Management, online erschienen am 10.09.2026. Verfasst von Xinran Yue und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Financial fraud detectors operate in a non-stationary environment in which illicit actors adapt, class prevalence changes, and labels arrive after investigation. This paper proposes ATGNN-SP, a drift-gated stable-plastic temporal graph neural network for real-time-compatible fraud scoring. Each directed transaction snapshot is converted into a 133-dimensional representation by a two-hop simplified graph convolution that separately propagates incoming, outgoing, second-order, and cross-direction information. A frozen stable multilayer perceptron preserves the initial concept, while a plastic copy is updated only when delayed prequential log loss exceeds a validation-derived control limit. Recent snapshots provide rapid adaptation and an anchor replay buffer limits forgetting. Experiments are executed on the real Elliptic Bitcoin transaction graph using a strict chronological protocol: time steps 1-29 for initial training, 30-34 for validation, and 35-49 for predict-then-update testing. Across three seeds, ATGNN-SP reaches F1 0.2649+/-0.0092 and average precision 0.2624+/-0.0193, improving the static graph MLP by 4.27% and 5.43% relative, respectively. A graph-aware gradient-boosting baseline obtains a slightly higher F1 of 0.2714, which is reported explicitly. The accompanying artifact contains all code, logs, and unedited result files; no experimental metric is synthesized or manually altered.
Zitieren
APA
Yue, X., Yang, J., Zhu, R., & Xu, Q. (2026). Adaptive Temporal Graph Neural Networks for Real-Time Financial Fraud Detection under Concept Drift. Highlights in Business, Economics and Management, 69, 239-250. https://doi.org/10.54097/c8364y03
Vancouver
Yue X, Yang J, Zhu R, Xu Q. Adaptive Temporal Graph Neural Networks for Real-Time Financial Fraud Detection under Concept Drift. Highlights in Business, Economics and Management. 2026;69:239-250. doi:10.54097/c8364y03
BibTeX
@article{Yue2026,
author = {Yue, Xinran and Yang, Jingyun and Zhu, Rufeng and Xu, Qiao},
title = {Adaptive Temporal Graph Neural Networks for Real-Time Financial Fraud Detection under Concept Drift},
journal = {Highlights in Business, Economics and Management},
year = {2026},
volume = {69},
pages = {239--250},
doi = {10.54097/c8364y03}
}
EUVIMED